INDEX

Explanations

words associated with cutting or chopping actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.gov

-0.15

 dopl

-0.14

 Tort

-0.14

acious

-0.14

 Rapid

-0.14

ctr

-0.14

NU

-0.14

 forCell

-0.14

SOLE

-0.13

_macros

-0.13

POSITIVE LOGITS

 Cutting

0.22

åĪĩ

0.22

 cutting

0.21

.cut

0.20

-cut

0.20

Cut

0.19

Cut

0.19

 excess

0.18

off

0.18

 Ð½Ð¾Ð¶

0.17

Activations Density 0.065%

words associated with cutting or chopping actions

No Comments

No Known Activations